MCP.so
Sign In

Typesense MCP Server

@avarant

About Typesense MCP Server

MCP server for Typesense

Basic information

Category

Other

License

MIT

Runtime

python

Transports

stdio

Publisher

avarant

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "typesense-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "main.py"
      ],
      "env": {
        "TYPESENSE_API_KEY": "xyz"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Typesense MCP Server?

A Model Context Protocol (MCP) server that provides a standardized interface to interact with Typesense, a fast open-source search engine. It is designed for developers using MCP-compatible clients (like Claude Desktop, Cursor, Zed, VS Code) to perform search operations, manage collections, and handle documents in Typesense through natural language commands.

How to use Typesense MCP Server?

Install uv, clone the repository to ~/typesense-mcp-server, then add the server to your MCP client’s configuration file (e.g., ~/.cursor/mcp.json or Claude Desktop config). Set the required environment variables (TYPESENSE_HOST, TYPESENSE_PORT, TYPESENSE_PROTOCOL, TYPESENSE_API_KEY). Run the server with the default STDIO transport or switch to HTTP transports for web clients.

Key features of Typesense MCP Server

  • Checks Typesense server health and lists all collections
  • Creates, describes, exports, deletes, and truncates collections
  • Creates, upserts, deletes, and batch-indexes documents
  • Imports documents from CSV data into a collection
  • Performs keyword search and vector similarity search on collections
  • Supports STDIO, legacy SSE, and Streamable HTTP transports

Use cases of Typesense MCP Server

  • Build an AI assistant that can search a Typesense-powered product catalog
  • Manage collection schemas and bulk-import documents from a conversational interface
  • Enable semantic vector search queries on text or embeddings stored in Typesense
  • Automate index maintenance tasks (e.g., truncate, export, delete) via MCP clients

FAQ from Typesense MCP Server

How do I install the Typesense MCP Server?

Install uv (e.g., via Homebrew on macOS), clone the GitHub repository, then configure your MCP client to launch the server with uv run main.py and the required environment variables.

What environment variables are required?

You must set TYPESENSE_HOST, TYPESENSE_PORT, TYPESENSE_PROTOCOL, and TYPESENSE_API_KEY. Optional variables include MCP_TRANSPORT, MCP_HOST, MCP_PORT, MCP_STATELESS_HTTP, and MCP_CORS_ORIGINS.

What MCP transports does this server support?

It supports STDIO (default), legacy SSE, and the newer Streamable HTTP transport. STDIO works with desktop clients; Streamable HTTP is recommended for web-based clients.

Can I use this server with a web client?

Yes. Use the Streamable HTTP transport (set MCP_TRANSPORT=streamable-http) and enable CORS with MCP_CORS_ORIGINS. Stateless mode (MCP_STATELESS_HTTP=true) is required for clients that don’t maintain persistent MCP sessions.

Does this server require a running Typesense instance?

Yes. The server communicates with an existing Typesense server. You must provide its host, port, protocol, and API key via environment variables.

Comments

More Other MCP servers